Lanxiang Hu PRO

Snyhlx's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper about 21 hours ago

JetSpec++: Foresight Parallel Drafting with Self Refinements

Paper • 2610.19792 • Published 19 days ago • 1

upvoted a paper about 22 hours ago

JetSpec++: Foresight Parallel Drafting with Self Refinements

Paper • 2610.19792 • Published 19 days ago • 1

liked a dataset 1 day ago

lmgame/WMEval-Lite

Viewer • Updated 5 days ago • 284 • 860 • 2

liked 2 models 2 days ago

JetSpec/jetspec-plus-plus-qwen3p8-27b

2B • Updated 13 days ago • 243 • 1

JetSpec/jetspec-plus-plus-qwen3-8b

1B • Updated 13 days ago • 215 • 1

upvoted a collection 2 days ago

JetSpec-plus-plus releases

Collection

Public JetSpec++ checkpoints: causal parallel drafters with (1) foresight drafting and (2) self refinement for lossless speculative decoding. • 2 items • Updated 4 days ago • 4

updated a collection 4 days ago

JetSpec-plus-plus releases

Collection

Public JetSpec++ checkpoints: causal parallel drafters with (1) foresight drafting and (2) self refinement for lossless speculative decoding. • 2 items • Updated 4 days ago • 4

published 4 models 4 days ago

JetSpec/jetspec-plus-plus-qwen3-8b

1B • Updated 13 days ago • 215 • 1

JetSpec/dspark-qwen3-8b-800k

2B • Updated 9 days ago • 25

JetSpec/dspark-qwen3p8-27b-800k

2B • Updated 9 days ago • 21

JetSpec/jetspec-plus-plus-qwen3p8-27b

2B • Updated 13 days ago • 243 • 1

authored 2 papers 3 months ago

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

Paper • 2606.18394 • Published Jun 25 • 36

d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation

Paper • 2601.07568 • Published Jan 12 • 2

upvoted a paper 3 months ago

Wonder: Video World Model Done Better

Paper • 2607.26037 • Published Jul 28 • 20

liked a model 3 months ago

JetSpec/jetspec-Qwen3.6-35B-A3B

0.5B • Updated Jun 17 • 92 • 11

liked a model 4 months ago

nvidia/Cosmos3-Super-Image2Video-4Step

Image-to-Video • 64B • Updated 10 days ago • 629 • 36

liked 2 datasets 4 months ago

markov-ai/gaming-500-hours

Viewer • Updated Jun 30 • 776 • 14.4k • 268

macrodata/WGO-Bench

Viewer • Updated Jul 13 • 100 • 2.22k • 19

upvoted a paper 4 months ago

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

Paper • 2606.28128 • Published Jun 26 • 55